Mapping Student Log Files With K-Means Clustering

Abstract

One of the important characteristics of an e-learning platform is that students can take the course at any time, and they are not required to complete all the available learning activities at one time. In moodle, data logs are valuable information that contains activities from course users and course teachers. The data recorded in the moodle data log can be in the form of activity data, assignment time (assignment timestamp), and ranking value or final grade (grade). Data log exploration of educational data mining can be used to facilitate monitoring and see what activities are often carried out by course participants on the moodle platform. One of the techniques used in data mining log data analysis is cluster analysis. Cluster analysis is the process of grouping data into groups whose members have similar characteristics. K-means Clustering is one of the algorithms of cluster analysis that is often used. Based on the output, it can be noted that the members of cluster 1 are students with ids 1,3,4,5, and 9. Then for cluster 2 is the student with id 2,8,10,12 which on cluster 2 the average student click is highest,. and the last cluster 3 is filled by students with ids 6, 7, and 11. It can be concluded that the second cluster is a collection of students who are active in accessing the LMS during learning.